© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 3842
    Prev
    Next
    INDEX
    Explanations

    discussion and action intents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pang
    0.72
    oo
    0.71
    o
    0.64
    ks
    0.64
    Oy
    0.63
    uest
    0.62
    ig
    0.62
     inescapable
    0.61
    yg
    0.61
    oj
    0.61
    POSITIVE LOGITS
     (~
    0.90
    <0x96>
    0.89
    робнее
    0.85
    viridis
    0.84
    鹭
    0.84
     Herbst
    0.84
     (_,
    0.84
     Hawk
    0.84
    Hawk
    0.83
    羰
    0.83
    Activations Density 0.191%

    No Known Activations